Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes beyond the annotations by disclosing that respondent weights stay in a temporary hosted workspace (no persistence), that a revision-bound review fingerprint is produced, and that execution is asynchronous. Annotations already cover idempotency and non-destructiveness, so this contextual layer is genuinely additive rather than redundant.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the purpose, followed by return content and the async/job pattern. Nothing is wasted, though the second sentence packs several diagnostics into a single clause.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Compensates for the absent output schema by naming the returned diagnostics (aggregate balance, trimming, effective-base, review fingerprint), which is valuable. However, for a 10-parameter required-input tool at 20% schema coverage, the complete omission of parameter meaning leaves a substantial gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 20% with 10 required parameters, so the description must carry the burden and largely does not. It alludes to 'population margins' (targets) and 'trimming' (trim) but never explains expectedRevision, tolerance, maxIterations, baseWeightId, or the workspaceToken/what-happens semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Preview explicit population margins against the saved active wave') and clarifies that it is a non-mutating dry-run of raking, which implicitly separates it from apply_raking_weights. It does not name the sibling explicitly, so routing relies on the preview/apply verb contrast rather than an overt statement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear operational context: it queues a hosted job and directs the agent to 'use get_job to retrieve its result,' which is a concrete alternative/callback path. It does not explicitly state when to prefer preview over apply_raking_weights, leaving that to inference from the verb.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.